{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T20:43:48Z","timestamp":1792961028170,"version":"4.5.0"},"reference-count":14,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2010,1]]},"abstract":"<jats:p>MapReduce advantages over parallel databases include storage-system independence and fine-grain fault tolerance for large jobs.<\/jats:p>","DOI":"10.1145\/1629175.1629198","type":"journal-article","created":{"date-parts":[[2009,12,21]],"date-time":"2009-12-21T14:08:04Z","timestamp":1261404484000},"page":"72-77","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":974,"title":["MapReduce"],"prefix":"10.1145","volume":"53","author":[{"given":"Jeffrey","family":"Dean","sequence":"first","affiliation":[{"name":"Systems Infrastructure Group of Google, Mountain View, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjay","family":"Ghemawat","sequence":"additional","affiliation":[{"name":"Systems Infrastructure Group of Google, Mountain View, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2010,1]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687731"},{"key":"e_1_2_1_2_1","unstructured":"Aster Data Systems Inc. In-Database MapReduce for Rich Analytics; http:\/\/www.asterdata.com\/product\/mapreduce.php.  Aster Data Systems Inc. In-Database MapReduce for Rich Analytics ; http:\/\/www.asterdata.com\/product\/mapreduce.php."},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the Seventh Symposium on Operating System Design and Implementation","author":"Chang F.","year":"2006","unstructured":"Chang , F. , Dean , J. , Ghemawat , S. , Hsieh , W.C. , Wallach , D.A. , Burrows , M. , Chandra , T. , Fikes , A. , and Gruber , R.E . Bigtable: A distributed storage system for structured data . In Proceedings of the Seventh Symposium on Operating System Design and Implementation ( Seattle, WA, Nov. 6--8). Usenix Association , 2006 ; http:\/\/labs.google.com\/papers\/bigtable.html Chang, F., Dean, J., Ghemawat, S., Hsieh, W.C., Wallach, D.A., Burrows, M., Chandra, T., Fikes, A., and Gruber, R.E. Bigtable: A distributed storage system for structured data. In Proceedings of the Seventh Symposium on Operating System Design and Implementation (Seattle, WA, Nov. 6--8). Usenix Association, 2006; http:\/\/labs.google.com\/papers\/bigtable.html"},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the Sixth Symposium on Operating System Design and Implementation","author":"Dean J.","year":"2004","unstructured":"Dean , J. and Ghemawat , S . MapReduce: Simplified data processing on large clusters . In Proceedings of the Sixth Symposium on Operating System Design and Implementation ( San Francisco, CA, Dec. 6--8). Usenix Association , 2004 ; http:\/\/labs.google.com\/papers\/mapreduce.html Dean, J. and Ghemawat, S. MapReduce: Simplified data processing on large clusters. In Proceedings of the Sixth Symposium on Operating System Design and Implementation (San Francisco, CA, Dec. 6--8). Usenix Association, 2004; http:\/\/labs.google.com\/papers\/mapreduce.html"},{"key":"e_1_2_1_5_1","unstructured":"Dewitt D. and Stonebraker M. MapReduce: A Major Step Backwards blogpost; http:\/\/databasecolumn.vertica.com\/database-innovation\/mapreduce-a-major-step-backwards\/  Dewitt D. and Stonebraker M. MapReduce: A Major Step Backwards blogpost; http:\/\/databasecolumn.vertica.com\/database-innovation\/mapreduce-a-major-step-backwards\/"},{"key":"e_1_2_1_6_1","unstructured":"Dewitt D. and Stonebraker M. MapReduce II blogpost; http:\/\/databasecolumn.vertica.com\/database-innovation\/mapreduce-ii\/  Dewitt D. and Stonebraker M. MapReduce II blogpost; http:\/\/databasecolumn.vertica.com\/database-innovation\/mapreduce-ii\/"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/945445.945450"},{"key":"e_1_2_1_8_1","unstructured":"Google. Protocol Buffers: Google's Data Interchange Format. Documentation and open source release; http:\/\/code.google.com\/p\/protobuf\/  Google. Protocol Buffers: Google's Data Interchange Format. Documentation and open source release; http:\/\/code.google.com\/p\/protobuf\/"},{"key":"e_1_2_1_9_1","unstructured":"Greenplum. Greenplum MapReduce: Bringing Next-Generation Analytics Technology to the Enterprise; http:\/\/www.greenplum.com\/resources\/mapreduce\/  Greenplum. Greenplum MapReduce: Bringing Next-Generation Analytics Technology to the Enterprise; http:\/\/www.greenplum.com\/resources\/mapreduce\/"},{"key":"e_1_2_1_10_1","unstructured":"Hadoop. Documentation and open source release; http:\/\/hadoop.apache.org\/core\/  Hadoop. Documentation and open source release; http:\/\/hadoop.apache.org\/core\/"},{"key":"e_1_2_1_11_1","unstructured":"Hadoop. Users list; http:\/\/wiki.apache.org\/hadoop\/PoweredBy  Hadoop. Users list; http:\/\/wiki.apache.org\/hadoop\/PoweredBy"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559865"},{"key":"e_1_2_1_14_1","first-page":"227","volume":"13","author":"Pike R.","unstructured":"Pike , R. , Dorward , S. , Griesemer , R. , and Quinlan , S. Interpreting the data: Parallel analysis with Sawzall. Scientific Programming Journal, Special Issue on Grids and Worldwide Computing Programming Models and Infrastructure 13 , 4, 227 -- 298 . http:\/\/labs.google.com\/papers\/sawzall.html Pike, R., Dorward, S., Griesemer, R., and Quinlan, S. Interpreting the data: Parallel analysis with Sawzall. Scientific Programming Journal, Special Issue on Grids and Worldwide Computing Programming Models and Infrastructure 13, 4, 227--298. http:\/\/labs.google.com\/papers\/sawzall.html","journal-title":"Infrastructure"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1629175.1629198","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1629175.1629198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:41:25Z","timestamp":1750250485000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1629175.1629198"}},"subtitle":["a flexible data processing tool"],"short-title":[],"issued":{"date-parts":[[2010,1]]},"references-count":14,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,1]]}},"alternative-id":["10.1145\/1629175.1629198"],"URL":"https:\/\/doi.org\/10.1145\/1629175.1629198","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,1]]},"assertion":[{"value":"2010-01-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}